The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

Although supervised deep learning has revolutionized speech and audio processing, it has
necessitated the building of specialist models for individual tasks and application scenarios …

Semi-supervised learning (SSL) improves model generalization by leveraging massive
unlabeled data to augment limited labeled samples. However, currently, popular SSL …

In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

Self-training and unsupervised pre-training have emerged as effective approaches to
improve speech recognition systems using unlabeled data. However, it is not clear whether …

We revisit self-training in the context of end-to-end speech recognition. We demonstrate that
training with pseudo-labels can substantially improve the accuracy of a baseline model. Key …

This paper introduces a new end-to-end text-to-speech (E2E-TTS) toolkit named ESPnet-
TTS, which is an extension of the open-source speech processing toolkit ESPnet. The toolkit …

Self-supervised speech models are powerful speech representation extractors for
downstream applications. Recently, larger models have been utilized in acoustic model …

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We
first exploit a large amount of unlabeled audio data via representation learning, where we …